Search

For Micro, Small and Medium Enterprises data is everything. If they lose their customer's data they may lose everything. They will lose their credibility and their entire business. A one-touch security solution is not feasible with its limited budget. The designed solution caters to the needs of an SME. An ARM-based low-cost solution is implemented. Raspberry Pi based security solution which comprises the features like Network Analysis, Vulnerability Analysis, Security Policy measures, Disaster Recovery and Backup. It also has the capability of a Firewall, DHCP Server, and proxy to route and filter the traffic. One component similar is OpenVAS but it is discontinued for ARM-based Architecture. Another component similar to one of the module is Pi-Hole, but it is used for adblocking. A single solution that comprises all the above-mentioned features and cost-effective is not available in the market. So we are proposing one.

Visual question answering (VQA), visual dialogs, visual chat bot are multi-discipline exploration problems, which is a blend of Natural Language Processing (NLP), Image feature extraction and Knowledge Reasoning (KR). Rather than captioning, which is naive approach of computer vision, VQA problems enhances the perspective by providing interactivity to ask domain specific as well as open ended questions to images and give us the insights based on image features or characteristics. Our research is the evaluate the performance of VQA on counting problems. Given an image, VQA model is expected to answer "how many" question type. We have used few pre-trained models for VQA and visual dialog and tabulated the findings of accuracy of predicted answer with the pre-defined ground truth.

This paper analysis the performance of Fuzzy PD+I and conventional PID controller on nonlinear systems. The nonlinear systems used are level control of a surge tank and cart pole system. Level control of a surge tank level system and angular position of cart pole system have been tracked using Fuzzy PD+I controller and conventional controller. Four type of membership functions Bell, Pi, Gaussian and Psigmoid are used in the fuzzy PD+I control of the nonlinear systems. Effects of different membership functions on the systems control have been compared with conventional PID controller. For four different membership functions besides control performance stability criterion also have been implemented using phase-plane method.

With the help of evolutionary concepts and behavior of biotic components of nature, many optimization algorithms were developed. Optimization techniques like Particle Swarm Optimization and Firefly Algorithms are among the latest research topics. Several advancements have also been made in these algorithms. This paper carves out a comparative analysis of Particle Swarm Optimization (PSO) and Firefly Algorithm (FFA) in detail along with simulation results carried out on some standard benchmark functions.

A major problem today for car owners is that they are in constant fear of having their vehicles stolen from a common parking lot or from outside their home. Image processing based real time vehicle theft detection and prevention system provide an ultimate solution for this problem. The system described in this paper automatically take photos of driver and compares his or her face with database to check whether he is an authenticated driver or not. He can have access to the vehicle only if he is an authenticated driver. If he is not an authenticated driver an alarm rings and electrical connections are not activated. The technology used here is face recognition and face detection in real time. As the photos are taken in real time, several problems like unequal illumination and changes in the background may affect the system. To overcome this problem DCT normalization and background cancellation algorithms are incorporated along with basic face detection and face recognition algorithm. In this paper software and hardware details of the system are discussed. Technologically system is simple, accurate and maintainable.

Being an inherently unstable system, active magnetic bearing, with its envisaged widespread applications, is a potential research area in today's scenario. So far many controllers including the H- Infinity controller has been developed but a generalized design is lacking. In this paper a generalized design of H- infinity controllers for Magnetic bearings is proposed along with a novel automatic weight selection algorithm for any specification and dimension of active magnetic bearings. The design procedure is validated by designing stable H infinity controllers for different AMB specifications. A detailed disturbance analysis and hence the efficacy of H infinity controller for disturbance rejection in AMB systems is investigated.